Machine Learning a General-Purpose Interatomic Potential for Silicon

Bartók, Albert P.; Kermode, James R.; Bernstein, Noam; Csänyi, Gábor

doi:10.1103/physrevx.8.041048

Cited by 406 publications

(541 citation statements)

References 224 publications

Supporting

Mentioning

501

Contrasting

Order By: Relevance

“…A typical example is the formation and propagation of cracks (Figure 2c), a microscopic effect that has tremendous importance for the macroscopic behavior of materials. [95] also correctly captures this qualitative behavior-but what is more, it recovers even subtle bond-rotation mechanisms that have previously been only seen in extremely expensive QM/MM simulations (mixing a quantummechanical method with a force field), using DFT at the crack tip. Because of the ongoing breaking and making of bonds during fracture, this is a very challenging problem for atomistic simulations.…”

Section: High Accuracy For Crystalline and Amorphous Materials: The Csupporting

confidence: 61%

“…[94] In these simulations, the Cmca phase of silicon had not been included in the fit but was readily discovered by the ML-potential-driven metadynamics simulations, which already points toward the applicability for crystal-structure searching. [95] Such a general potential should be able to accurately describe a very wide range of atomic configurations, including multiple phases, surfaces, and defects, for which the training database is explicitly "designed," but at the same time give sensible results for completely new kinds of configurations (e.g., structures found during systematic random structure search, or more complicated structural defects that were not included in the training but may occur in experiment). [80] Subsequently, silicon served to explore the question as to whether a "general-purpose" ML potential can be created for a given element.…”

Section: High Accuracy For Crystalline and Amorphous Materials: The Cmentioning

confidence: 99%

“…[80] Subsequently, silicon served to explore the question as to whether a "general-purpose" ML potential can be created for a given element. [95] The first necessary test for the resulting potential is the performance in regard to the "usual" quality indicators, which includes standard material properties that are relevant for practical applications (such as the bulk and shear modulus). Following this logic, a systematic database of reference configurations was constructed for silicon (Figure 2a).…”

Section: High Accuracy For Crystalline and Amorphous Materials: The Cmentioning

confidence: 99%

“…Because of the ongoing breaking and making of bonds during fracture, this is a very challenging problem for atomistic simulations. [95] We note that tests for extrapolation are also done for NN potentials:, e.g., by fitting several networks in parallel and determining the variance between them. [99] The ML potential described in ref.…”

Section: High Accuracy For Crystalline and Amorphous Materials: The Cmentioning

confidence: 99%

“…One such tool is NMR, where shifts can be computed from first principles (Figure 2d). [95] Structures were visualized using VESTA. [102] In these studies, the authors emphasize the importance of having a flexible potential that can treat the structurally very different local environments that occur during the formation and growth of crystallites in the disordered phase: seed nuclei might look very different from the corresponding bulk phases that grow out of them.…”

Section: High Accuracy For Crystalline and Amorphous Materials: The Cmentioning

confidence: 99%

See 4 more Smart Citations

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

2019

Self Cite

View full text Add to dashboard Cite

In pursuit of this goal, atomic-scale computer simulations have long been a central approach, and two major families of methods are routinely used today. On the one hand, there are quantum-mechanical simulations, in which we solve Schrödinger's equation for the electronic structure of molecular and periodic systems, most widely based on density-functional theory (DFT). [6][7][8] These methods provide (largely) reliable results for structural models of materials that normally contain a few tens or hundreds of atoms. State-of-the-art DFT methods can be applied to many material classes, and they are increasingly used for high-throughput screening and "in silico" (computer-based) design of materials: new compositions and previously unknown structures have been identified in DFT searches and subsequently experimentally realized. [5,[9][10][11] On the other hand, interatomic potential models ("force fields"), parameterizing interactions between atoms with (relatively) simple functional forms, are widely used in materials science to describe matter in molecular dynamics (MD) simulations. These simulations grant access to larger time and length scales, reaching system sizes of up to hundreds of thousands of atoms. [12] In parameterizing these potentials, a certain physical form of the atomic interactions is assumed, often in terms of bond distances, angles, and so on, and physical properties such as equilibrium lattice parameters or elastic constants enter the fitting of the potential. For this reason, such potentials are often called "empirical." They are several orders of magnitude faster than DFT, but necessarily less accurate and less easily transferable.In this Progress Report, we highlight recent developments in "machine-learned" interatomic potentials, which represent a rapidly growing field that promises to do away with the aforementioned trade-offs. Over the last year, there has been a surge of interest in machine learning (ML) methodology: part of it is due to the dramatic growth of ML throughout the scientific disciplines, and part of it is due to tangible success stories of ML-based interatomic potentials that are now beginning to emerge. We will argue that this is an exciting development with very practical implications, currently on the verge of moving from a somewhat specialized new technology to everyday applicability, poised to enhance and complement the communities' existing strengths in computational materials modeling. We will show selected applications of ML potentials to problems in materials science, discuss the current limitations (and possible pitfalls), and outline what we expect to be interesting directions for the development of the field in the coming years.Atomic-scale modeling and understanding of materials have made remarkable progress, but they are still fundamentally limited by the large computational cost of explicit electronic-structure methods such as density-functional theory. This Progress Report shows how machine learning (ML) is currently enabling a new degree of realism in materi...

show abstract

Section: High Accuracy For Crystalline and Amorphous Materials: The Csupporting

confidence: 61%

Section: High Accuracy For Crystalline and Amorphous Materials: The Cmentioning

confidence: 99%

Section: High Accuracy For Crystalline and Amorphous Materials: The Cmentioning

confidence: 99%

Section: High Accuracy For Crystalline and Amorphous Materials: The Cmentioning

confidence: 99%

Section: High Accuracy For Crystalline and Amorphous Materials: The Cmentioning

confidence: 99%

See 3 more Smart Citations

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

2019

Self Cite

View full text Add to dashboard Cite

show abstract

Cluster Fragments in Amorphous Phosphorus and their Evolution under Pressure

2021

View full text Add to dashboard Cite

such as "ab initio" molecular dynamics (AIMD). ML-based interatomic potentials, therefore, are beginning to be applied to a range of challenging materials-science research questions, such as the modeling of phase-change memory materials, [12][13][14] catalysts, [15] or battery materials. [16] Recently, a number of "general-purpose" ML potentials have been reported, which can accurately describe a broad range of atomic configurations and materials properties-including silicon, [17] carbon, [18] aluminum, [19,20] and the binary Ga-As system. [21] The hope for such potentials is to enable "off-the-shelf" use without further modification: for example, the aforementioned silicon ML potential has been used to study complex structural transitions under pressure [22] or unusual mechanical properties of amorphous silicon (a-Si). [23] The starting point for the present study is a general-purpose Gaussian approximation potential (GAP) ML model for bulk and nanostructured phosphorus-which was shown to be flexible enough to be applicable to the pressure-induced liquidliquid phase transition from the molecular fluid to the network liquid, whilst also accurately describing the crystalline allotropes and the layered structure of phosphorene. [24] This GAP is now set to facilitate even more challenging studies on more extended length or time scales, and the exploration of other structurally complex phases for which it has not been explicitly "trained", such as amorphous phosphorus (a-P).Research interest in a-P has grown because of emerging applications in batteries. [25][26][27][28] As a commercially available anode material, red phosphorus provides a large cation-storage ability with high theoretical capacities by forming binary X-P compounds (X = Li, Na, K), but it suffers from low conductivity and a large volumetric change during cycling. [29] As discussed in ref. [30], these issues can be ameliorated by creating composites of a-P and carbonaceous materials: on the one hand, increasing electronic conductivity; [31,32] on the other hand, minimizing the mechanical stress induced by volume changes. [30,33] The structure and properties of phosphorus itself are clearly important for battery applications: for example, experimental work showed that the size of a-P particles in phosphoruscarbon composite anodes has an effect on the electrochemical performance, [34] and in situ transmission electron microscopy (TEM) revealed images of red phosphorus segments within a carbon nanofiber. [35] Computationally, structurally ordered phases have been studied with density-functional theory (DFT; Amorphous phosphorus (a-P) has long attracted interest because of its complex atomic structure, and more recently as an anode material for batteries. However, accurately describing and understanding a-P at the atomistic level remains a challenge. Here, it is shown that large-scale molecular-dynamics simulations, enabled by a machine-learning (ML)-based interatomic potential for phosphorus, can give new insights into the atomic structure of a-P and how...

show abstract

Construction of High Accuracy Machine Learning Interatomic Potential for Surface/Interface of Nanomaterials—A Review

Wan,

He,

Shi

2023

Advanced Materials

View full text Add to dashboard Cite

The inherent discontinuity and unique dimensional attributes of nanomaterial surfaces and interfaces bestow them with various exceptional properties. These properties, however, also introduce difficulties for both experimental and computational studies. The advent of machine learning interatomic potential (MLIP) addresses some of the limitations associated with empirical force fields, presenting a valuable avenue for accurate simulations of these surfaces/interfaces of nanomaterials. Central to this approach is the idea of capturing the relationship between system configuration and potential energy, leveraging the proficiency of machine learning (ML) to precisely approximate high‐dimensional functions. This review offers an in‐depth examination of MLIP principles and their execution, and elaborates on their applications in the realm of nanomaterial surface and interface systems. We also discuss the prevailing challenges faced by this potent methodology.This article is protected by copyright. All rights reserved

show abstract

Machine Learning a General-Purpose Interatomic Potential for Silicon

Cited by 406 publications

References 224 publications

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

Cluster Fragments in Amorphous Phosphorus and their Evolution under Pressure

Construction of High Accuracy Machine Learning Interatomic Potential for Surface/Interface of Nanomaterials—A Review

Contact Info

Product

Resources

About